菜单
Use when CLAUDE.md or CLAUDE-*.md memory-bank files need creating, auditing, updating, or syncing with the codebase — after significant code changes, when documented patterns contradict the implementation, at session end to capture learnings, or when context files have grown stale or bloated.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Design Apple-style iOS/macOS interfaces following Human Interface Guidelines. Creates HIG-compliant components with SF Symbols, San Francisco typography, and proper accessibility. Supports optional modern effects. Use when designing Apple-style UI, iOS/macOS interfaces, HIG-compliant components, or implementing design system specifications.
Offload mechanical, well-specified coding work (refactors, renames, boilerplate, formatting passes, applying a pattern across many files) to `canaryclaude`, which is Claude Code routed through the user's own CanaryLLM proxy. Cheap and fast enough to fan out — pick a small/fast model like `gemini/gemini-2.5-flash` (or `gemini-2.5-flash-lite`, or local `lmstudio/qwen3.6-27b-mlx`) for the subagent. Use whenever a task is execution-heavy but reasoning-light — code transformations where you already know the answer and just need the typing done. Use even if the user hasn't named canaryclaude: if you're about to do a dozen near-identical edits, or apply a clearly-specified refactor across multiple files, this skill applies. Always background canaryclaude calls and parallelize them — even fast models take 15–60s per task, so it shines when many run concurrently while you do real reasoning work.
Call the CanaryLLM gateway (canaryllm.canarycoders.es) — a multi-provider LLM API for chat completions, image/video/audio/music/dialogue generation, vision (object & face detection, custom model training), conversational AI agents, and drop-in OpenAI/Anthropic/Responses-compatible endpoints. Use this whenever the user wants to hit CanaryLLM / CanaryLLM API / the canary gateway, generate media through it, point an existing tool or SDK at it, or write code/scripts that call any canaryllm.canarycoders.es endpoint — even if they don't paste the spec. Knows the async queue (submit → poll) workflow that the native endpoints require, the Bearer-token auth convention, and which endpoints are synchronous vs queued.
Use when asked for a thorough, deep, or multi-angle review of a branch, PR, or recent changes — or when a diff touches error handling, catch blocks, fallbacks, new types, or test coverage and deserves more than a quick single pass.
Interface directly with Gem0 (the CouchDB-backed headless CMS / database-as-a-service) over HTTP using API keys — create tables (schemes), modify table schemas, and add/update/query/delete rows. Use this skill whenever the user mentions Gem0, gem0.dev, GemAPI, GemBackend, pillow endpoints, Gem0 schemes/collections/tables, the @gemzero0 SDK, GemSync, or wants any script/integration/agent that reads or writes data in Gem0 — even if they don't say "API" or only say "store this in my CMS".
Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use Herdr to inspect or control panes, tabs, workspaces, terminals, commands, or communication with another agent. Do not use merely because a task could benefit from a background terminal, delegation, or parallel work. Requires HERDR_ENV=1.
| name | memory-bank |
| description | Use when CLAUDE.md or CLAUDE-*.md memory-bank files need creating, auditing, updating, or syncing with the codebase — after significant code changes, when documented patterns contradict the implementation, at session end to capture learnings, or when context files have grown stale or bloated. |
One skill for the whole memory-bank lifecycle (CLAUDE.md plus the CLAUDE-activeContext / patterns / decisions / troubleshooting / config-variables files). Replaces the claude-md-management and codebase-documenter plugins and the update-memory-bank, analyze-codebase, and cleanup-context commands — if any of those are still visible, use this skill instead.
capture (end of session / "remember this"): reflect on what context was missing this session — commands discovered, style patterns, config quirks, gotchas. Add the few that will recur to the right file: shared → CLAUDE.md, session state → CLAUDE-activeContext.md, conventions → CLAUDE-patterns.md, rationale → CLAUDE-decisions.md, proven fixes → CLAUDE-troubleshooting.md. Create a memory-bank file only if a learning belongs there and the file doesn't exist yet.
sync ("docs don't match the code"): for each memory-bank file, check its
claims against the implementation; fix what drifted, flag what you're unsure
about. For a large sweep, spawn one general-purpose subagent per file on
sonnet (fact-checking docs against code is execution-heavy — see the
model-routing rule in CLAUDE.md) and have each return a list of stale claims
with file:line evidence.
audit ("check/improve our CLAUDE.md files"): find all CLAUDE.md files
(fd CLAUDE.md), then per file: commands that no longer exist, wrong paths,
duplicated guidance, bloat (cut it via optimize mode), missing load-bearing
context. Report before editing.
optimize ("context files too big"): dedupe across files, collapse narratives into single-line facts, move project-specific detail out of the global file. Show the diff of what gets cut.
